Hi, I’m Chandan, a Senior Researcher at Microsoft Research, dedicated to the exploration of interpretable machine learning. My journey began during my PhD at UC Berkeley, where I cultivated the habit of meticulously enhancing my notes. I’ve shared these findings on this website in hopes that they might prove useful to you 🙂
What You’ll Find Here
Source and Presentation Materials
The presentation materials folder offers source files for my teaching presentations, which include:
- ML slides from Berkeley CS 189
- AI slides from Berkeley CS 188
- Interpretability workshop
- Disentangled interpretations
Research and Class Notes
In the research_overviews folder, you will find valuable summaries of recent papers across multiple domains:
- Interpretability
- Causal Inference
- Transfer Learning
- Uncertainty
- Deep Learning Theory
- Complexity
- Scattering Transform
- Deep Learning in Neuroscience
Notes and Cheat Sheets
Our collection of markdown notes and cheat sheets spans various fields of computer science, statistics, and neuroscience:
- Interpretability Cheat Sheet
- Computational Neuroscience
- Causal Inference Notes
- Classification Notes
- Linear Algebra
- Information Theory
- Computer Vision
How to Get Started with Using these Resources
Utilizing my notes and presentations can enhance your understanding of interpretability in machine learning. Here’s how to make the most of them:
- Navigate through the research overviews and identify papers aligned with your interests.
- Download the presentation files for tailored studies or group discussions.
- Refer to the cheat sheets as quick references while working on your projects.
Troubleshooting Tips
If you encounter any issues while exploring the resources, here are some suggestions:
- Check your internet connection to ensure you can access links.
- If any presentations do not load, try clearing your browser cache or using a different browser.
- For unclear content, feel free to reach out via @csinva for quick clarification.
For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.
At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.
Recent Blog Posts
Take a look at a few topics discussed in my blog:
Happy Reading!